Dynamic portfolio rebalancing through reinforcement learning

Abstract

Portfolio managements in financial markets involve risk management strategies and opportunistic responses to individual trading behaviours. Optimal portfolios constructed aim to have a minimal risk with highest accompanying investment returns, regardless of market conditions. This paper focuses on providing an alternative view in maximising portfolio returns using Reinforcement Learning (RL) by considering dynamic risks appropriate to market conditions through dynamic portfolio rebalancing. The proposed algorithm is able to improve portfolio management by introducing the dynamic rebalancing of portfolios with vigorous risk through an RL agent. This is done while accounting for market conditions, asset diversifications, risk and returns in the global financial market. Studies have been performed in this paper to explore four types of methods with variations in fully portfolio rebalancing and gradual portfolio rebalancing, which combine with and without the use of the Long Short-Term Memory (LSTM) model to predict stock prices for adjusting the technical indicator centring. Performances of the four methods have been evaluated and compared using three constructed financial portfolios, including one portfolio with global market index assets with different risk levels, and two portfolios with uncorrelated stock assets from different sectors and risk levels. Observed from the experiment results, the proposed RL agent for gradual portfolio rebalancing with the LSTM model on price prediction outperforms the other three methods, as well as returns of individual assets in these three portfolios. The improvements of the returns using the RL agent for gradual rebalancing with prediction model are achieved at about 27.9–93.4% over those of the full rebalancing without prediction model. It has demonstrated the ability to dynamically adjust portfolio compositions according to the market trends, risks and returns of the global indices and stock assets.

Enhancing portfolio management using artificial intelligence: literature review

“…In contrast, corridor strategies set thresholds or bands around target allocations, prompting rebalancing when assets deviate beyond these bounds. Additionally, more recent research by Lim et al ( 2022 ) has expanded the discussion by considering transaction costs, identifying two distinct approaches: complete portfolio rebalancing and gradual portfolio rebalancing. Complete portfolio rebalancing targets swift asset reallocation within a single trading day, while gradual rebalancing spreads adjustments across multiple trading days to minimize costs.…”

“…This approach outperformed benchmarks in terms of returns and risk. Lim et al ( 2022 ) employed an RL agent, introducing four distinct combinations of portfolio adjustments and price prediction models: (1) complete portfolio balancing without the Long Short-Term Memory (LSTM) prediction model, (2) complete portfolio balancing with the LSTM prediction model, (3) gradual portfolio balancing without the LSTM prediction model, and (4) gradual portfolio balancing with the LSTM prediction. Therefore, portfolio rebalancing utilizing the Recurrent RL (RRL) method and an adjusted objective function considering transaction costs and market risk aligns to develop efficient learning algorithms in RL, as discussed by Szepesvári ( 2010 ).…”

Can Interpretable Reinforcement Learning Manage Prosperity Your Way?

“…RL has been extensively applied to stock portfolio management [20,21,22,23,24,25], but not yet to holistic asset management; the lack of model transparency may be a contributing factor. Interpretation of RL agents typically follows model training [26,27,28]; our ambition is to impose a desired characteristic behaviour during training, thus making it an intrinsic property of the agent.…”

Dynamic Portfolio Rebalancing with Lag-Optimised Trading Indicators Using Serofam and Genetic Algorithms

“…This is because in a bearish market, the likelihood of losses is greater. Investors tend to try to minimize risks and losses (Lim, Cao, & Quek, 2022). Likewise, when a buy signal is detected from a higher risk asset, the portfolio assets will be reallocated from a lower risk asset to the higher risk asset.…”